Training in progress, step 99, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e532ba35b27a83231fb7a3d9482bdab0258777ddf1ca7b14a19a7858e7ff7abd
+oid sha256:ef93c783fe7f0a703386cb69534b5df642a3c0d6062012a6dc5acc0a419c2243
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d62b3280bd58e6ba69d1a44e508962515322947a768647efd13051010cf004
+oid sha256:96e27ccd1ac0b8310b5ac56224f08417b3796d6ff76c8b9966461f952b9bf5d0
 size 82460660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78621a855fd37cdb7268e6e6d1f9e4acf45018d8787685d4b90b28e3f57b0224
+oid sha256:98ceeb98bc98a108f218bca849514ba73d1501e8edab441d125301a6929ed105
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2857142857142856,
+  "epoch": 1.4142857142857144,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 7.298,
       "eval_steps_per_second": 0.928,
       "step": 90
+    },
+    {
+      "epoch": 1.3285714285714285,
+      "grad_norm": 1.4942926168441772,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.5905,
+      "step": 93
+    },
+    {
+      "epoch": 1.3714285714285714,
+      "grad_norm": 1.4011179208755493,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.5002,
+      "step": 96
+    },
+    {
+      "epoch": 1.4142857142857144,
+      "grad_norm": 1.3108495473861694,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.5893,
+      "step": 99
+    },
+    {
+      "epoch": 1.4142857142857144,
+      "eval_loss": 0.6319289803504944,
+      "eval_runtime": 16.1594,
+      "eval_samples_per_second": 7.302,
+      "eval_steps_per_second": 0.928,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4728493776437248e+17,
+  "total_flos": 2.72450330724139e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null